logs

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, so "Read-only" is redundant, but the description adds genuinely non-structured behavior: bounded snapshot semantics, a default tail of 200, a hard cap of 10000, and non-streaming polling. It doesn't say what happens when the cap is hit or whether truncation is signaled, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with what the tool returns and its bounds, then the non-streaming caveat, then the workflow. No sentence is filler and nothing essential is buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly states the return type (text) and its size bounds, and it covers the zero-required-parameter calling pattern. Minor gaps remain around truncation signaling and the interaction between `since` and `tail` when both are supplied.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75%, and the description usefully fills the largest gap by supplying the `tail` default of 200 lines and its 10000 ceiling, which the schema states only as a maximum. `since` and `services` semantics come from the schema, and the description supplies an operational hint via the services-narrowing workflow.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource ("bounded snapshot of recent logs from the running stack") plus the shape of the result ("returned as text"). It is immediately distinguishable from siblings like status, runtime_check, and doctor, which do not return raw log text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent: "Use `status` first to find which service is failing, then pass services to narrow the output" names both the alternative and the condition that selects it. It also rules out a common misuse case with "Not a stream: call it again for newer lines."

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.